Emotions detection using facial expressions recognition and EEG

The study of emotions in human-computer interaction has increased in the recent years. With successful classification of emotions, we could get instant feedback from users, gain better understanding of the human behavior while using the information technologies and thus make the systems and user interfaces more emphatic and intelligent. In our work, we focused on two approaches, namely emotions detection using facial expressions recognition and electroencephalography (EEG). Firstly, we analyzed existing tools that employ facial expressions recognition for emotion detection and compared them in a case study in order to acquire the notion of the state-of-the-art. Secondly, we proposed a method of emotion detection using EEG that employs existing machine learning approaches. We evaluated it on a standard dataset as well as with an experiment, in which participants watched emotion-evoking music videos. We used Emotiv Epoc to capture participants' brain activity. We achieved 53% accuracy in classifying a correct emotion, which is better compared to 19% accuracy of the existing facial expression based tool Noldus FaceReader.